# How I failed machine learning in medical imaging -- shortcomings and recommendations

arXiv: https://arxiv.org/abs/2103.10292 · HTML: https://mlsanity.com/paper/2103.10292/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 122 references that are in the map.
- First posted on arXiv 18 Mar 2021.

## Builds on (most cited first, 30 of 39)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Confounding variables can degrade generalization performance of radiological deep learning models](https://mlsanity.com/paper/1807.00431/) (2018)
- [A large annotated medical image dataset for the development and evaluation of segmentation algorithms](https://mlsanity.com/paper/1902.09063/) (2019)
- [Are we done with ImageNet?](https://mlsanity.com/paper/2006.07159/) (2020)
- [A Metric Learning Reality Check](https://mlsanity.com/paper/2003.08505/) (2020)
- [Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet](https://mlsanity.com/paper/1904.00760/) (2019)
- [Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning](https://mlsanity.com/paper/2002.05651/) (2020)
- [Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift](https://mlsanity.com/paper/1810.11953/) (2018)
- [A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises](https://mlsanity.com/paper/2008.09104/) (2020)
- [Deep Learning: A Critical Appraisal](https://mlsanity.com/paper/1801.00631/) (2018)
- [Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imaging](https://mlsanity.com/paper/1909.12475/) (2019)
- [Accounting for Variance in Machine Learning Benchmarks](https://mlsanity.com/paper/2103.03098/) (2021)
- [Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches](https://mlsanity.com/paper/1907.06902/) (2019)
- [Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis](https://mlsanity.com/paper/1804.06353/) (2018)
- [Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models](https://mlsanity.com/paper/2007.03051/) (2020)
- [Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans](https://mlsanity.com/paper/2008.06388/) (2020)
- [Should we really use post-hoc tests based on mean-ranks?](https://mlsanity.com/paper/1505.02288/) (2015)
- [Troubling Trends in Machine Learning Scholarship](https://mlsanity.com/paper/1807.03341/) (2018)
- [Convolutional Neural Networks for Classification of Alzheimer's Disease: Overview and Reproducible Evaluation](https://mlsanity.com/paper/1904.07773/) (2019)
- [Why rankings of biomedical image analysis competitions should be interpreted with care](https://mlsanity.com/paper/1806.02051/) (2018)
- [On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law](https://mlsanity.com/paper/2005.09241/) (2020)
- [Can we trust deep learning models diagnosis? The impact of domain shift in chest radiograph classification](https://mlsanity.com/paper/1909.01940/) (2019)
- [Detect and Correct Bias in Multi-Site Neuroimaging Datasets](https://mlsanity.com/paper/2002.05049/) (2020)
- [Cross-validation failure: small sample sizes lead to large error bars](https://mlsanity.com/paper/1706.07581/) (2017)
- [Exploring large scale public medical image datasets](https://mlsanity.com/paper/1907.12720/) (2019)
- [Reproducibility in Machine Learning for Health](https://mlsanity.com/paper/1907.01463/) (2019)

## Built on by (most cited first, 30 of 37)

- [Generative models improve fairness of medical classifiers under distribution shifts](https://mlsanity.com/paper/2304.09218/) (2023)
- [Artificial intelligence in digital pathology: a systematic review and meta-analysis of diagnostic test accuracy](https://mlsanity.com/paper/2306.07999/) (2023)
- [Ctrl-GenAug: Controllable Generative Augmentation for Medical Sequence Classification](https://mlsanity.com/paper/2409.17091/) (2024)
- [Evaluating Synthetic Data Generation for Domain Generalization in Fetal Brain MRI Segmentation](https://mlsanity.com/paper/2411.06842/) (2024)
- [MMBU: A Massive Multi-modal Biomedical Understanding Benchmark to Probe the Perception Capabilities of Vision-Language Models](https://mlsanity.com/paper/2606.06696/) (2026)
- [Inventing a coin-flip classifier: Accounting for multiplicity in machine learning benchmark performance](https://mlsanity.com/paper/2303.07272/) (2023)
- [Measuring Model-Induced Discrimination via Efficient Fairness Approximation](https://mlsanity.com/paper/2405.09251/) (2024)
- [How many measurements are enough? Bayesian recovery in inverse problems with general distributions](https://mlsanity.com/paper/2505.10630/) (2025)
- [Vision-language models for chest radiography do not always need the image](https://mlsanity.com/paper/2606.17710/) (2026)
- [State of Abdominal CT Datasets: A Critical Review of Bias, Clinical Relevance, and Real-world Applicability](https://mlsanity.com/paper/2508.13626/) (2025)
- [Medical Imaging AI Competitions Lack Fairness](https://mlsanity.com/paper/2512.17581/) (2025)
- [Physics from Video: Identifiability of Time-Invariant Second-Order ODEs under Minimal Trajectory Conditions](https://mlsanity.com/paper/2606.00115/) (2026)
- [A Leakage-Aware Comparative Benchmark of Machine Learning, Deep Learning, and Transformer Models for Reliable Leukemia Detection](https://mlsanity.com/paper/2606.24944/) (2026)
- [RadPRISM: Schema-stratified radiology-report supervision for concept-disentangled image representations and visual grounding](https://mlsanity.com/paper/2608.00147/) (2026)
- [Twin: Tuning Learning Rate and Weight Decay of Deep Homogeneous Classifiers without Validation](https://mlsanity.com/paper/2403.05532/) (2024)
- [Predicting Brain Morphogenesis via Physics-Transfer Learning](https://mlsanity.com/paper/2509.05305/) (2025)
- [GP-VM×SMA: Benchmarking General-Purpose Vision Models and Specialized Architectures for 2D Medical Image Segmentation](https://mlsanity.com/paper/2603.13044/) (2026)
- [JDCNet: Confidence-Gated Privileged-Modality Distillation for Cost-Preserving X-ray Inference](https://mlsanity.com/paper/2603.29167/) (2026)
- [Not All Forgetting Is Equal: Retention Dynamics in Fine-Tuned Image Classifiers](https://mlsanity.com/paper/2604.11508/) (2026)
- [On Hallucinations in Inverse Problems: Fundamental Limits and Provable Assessment Methods](https://mlsanity.com/paper/2605.13146/) (2026)
- [MicroscopyMatching: Towards a Ready-to-use Framework for Microscopy Image Analysis in Diverse Conditions](https://mlsanity.com/paper/2605.14980/) (2026)
- [Which Anatomy Matters Under Limited Labels? A Data-Efficient Anatomy-Aware Benchmark for Cardiac Pathology Prediction](https://mlsanity.com/paper/2606.06509/) (2026)
- [Feynman Kac Reweighted Schr"odinger Bridge Matching for Surface-Based Tau PET Harmonization](https://mlsanity.com/paper/2606.17420/) (2026)
- [When, Where, and How: Adaptive Binning for Tabular Self-Supervised Learning](https://mlsanity.com/paper/2606.19827/) (2026)
- [Agentic AI in medicine: architectures, applications, evaluation, and challenges for clinical translation](https://mlsanity.com/paper/2607.25489/) (2026)
- [Similarity Weighted Aggregation with Global Differential Privacy for Federated Brain Lesion Segmentation](https://mlsanity.com/paper/2608.00872/) (2026)
- [When Oracle Conditioning Misleads Deployment: Conditioning-Availability Bias in Echocardiographic Segmentation](https://mlsanity.com/paper/2608.03342/) (2026)
- [B-MIM: Biased Masked Image Modeling for Generalizable Segmentation of Fine-Grained Anatomical Structures](https://mlsanity.com/paper/2608.24364/) (2026)
- [MedSegBenchmarker: A Raw-Count-First Framework for Controlled 2D Medical Image Segmentation Benchmarks](https://mlsanity.com/paper/2608.29677/) (2026)
- [Self-supervised Pre-training Helps Retinal Disease Progression Modelling Most When Data Is Scarce](https://mlsanity.com/paper/2609.12834/) (2026)

## Abstract (arXiv)

Medical imaging is an important research field with many opportunities for improving patients' health. However, there are a number of challenges that are slowing down the progress of the field as a whole, such optimizing for publication. In this paper we reviewed several problems related to choosing datasets, methods, evaluation metrics, and publication strategies. With a review of literature and our own analysis, we show that at every step, potential biases can creep in. On a positive note, we also see that initiatives to counteract these problems are already being started. Finally we provide a broad range of recommendations on how to further these address problems in the future. For reproducibility, data and code for our analyses are available on urlhttps://github.com/GaelVaroquaux/mlmedimagingfailures